MapReduce自定义分组比较器

数据:
Input:
20 21
50 51
50 53
50 52
50 54
60 51
60 53
60 52
60 56
60 57
70 58
60 61
70 54
70 55
70 56
70 57
70 58
Output:
20 21
50 54
60 61
70 58
代码:
package MapReducer05;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.log4j.BasicConfigurator;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

public class WordCountGroup {
    public static class MyMapper extends Mapper<LongWritable, Text, MyWri, NullWritable>{

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String[] str = value.toString().split(" ");
            MyWri mw = new MyWri();
            mw.setFirst(Integer.parseInt(str[0]));
            mw.setLast(Integer.parseInt(str[1]));
            context.write(mw, NullWritable.get());
        }
    }
    public static class MyReducer extends Reducer<MyWri, NullWritable, MyWri, NullWritable> {
        @Override
        protected void reduce(MyWri key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        	//每个分组一个Iterable,以第一个字段分组
        	//只输出第一key,即第一个字段相同中的第二个字段最大的key
            int flag = 0;
            for(NullWritable nw : values){
                context.write(key, nw);
                flag = 1;
                if(flag==1) break;
            }
            //等context.write(key, NullWritable.get());
        }
    }
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
    	//System.setProperty("hadoop.home.dir", "F:\\hadoop-2.6.4");
        Configuration conf = new Configuration();
        BasicConfigurator.configure();
        Job job = Job.getInstance(conf, "mr");

        job.setJarByClass(WordCount.class);
        job.setMapperClass(MyMapper.class);
        job.setMapOutputKeyClass(MyWri.class);
        job.setMapOutputValueClass(NullWritable.class);
		//添加分组比较器
        job.setGroupingComparatorClass(MyGroupCompartor.class);

        job.setReducerClass(MyReducer.class);
        job.setOutputKeyClass(MyWri.class);
        job.setOutputValueClass(NullWritable.class);

        FileInputFormat.addInputPath(job, new Path("C:\\Users\\Chen\\Desktop\\input\\secondarysort"));
        FileOutputFormat.setOutputPath(job, new Path("C:\\Users\\Chen\\Desktop\\20"));

        System.exit(job.waitForCompletion(true)?0:1);


    }
}
//继承WritableComparator类实现分组比较器
class MyGroupCompartor extends WritableComparator{
    public MyGroupCompartor(){
        super(MyWri.class,true);
    }
    @Override
    public int compare(WritableComparable o1, WritableComparable o2) {
    	//按第一个字段进行分组
        MyWri mw1 = (MyWri)o1;
        MyWri mw2 = (MyWri)o2;
        return mw1.getFirst()-mw2.getFirst();
    }
}
//自定义Writable类
class MyWri implements WritableComparable<MyWri>{
    private int first;
    private int last;
    @Override
    public int compareTo(MyWri o) {
        int ff = this.first-o.first;
        if(ff==0){
            return o.last-this.last;
        } else {
            return ff;
        }
    }
    public MyWri(){}
    public MyWri(int first, int last) {
        this.first = first;
        this.last = last;
    }

    @Override
    public String toString() {
        return this.first+" "+this.last;
    }

    @Override
    public void write(DataOutput out) throws IOException {
        out.writeInt(first);
        out.writeInt(last);
    }

    @Override
    public void readFields(DataInput in) throws IOException {
        this.first = in.readInt();
        this.last = in.readInt();
    }

    public void setFirst(int first) {
        this.first = first;
    }

    public void setLast(int last) {
        this.last = last;
    }

    public int getFirst() {
        return first;
    }

    public int getLast() {
        return last;
    }
}


  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
MapReduce是一种大数据处理框架,它能够在分布式集群上进行并行计算。其中,自定义比较器MapReduce的一种功能,允许用户定义自己的比较方法来排序输出结果。 使用自定义比较器可以实现复杂的排序逻辑,而不是仅仅使用基本的字典序排序。例如,可以使用自定义比较器来按照日期、数字或其他自定义字段排序。 使用自定义比较器的方法是在MapReduce程序中实现自定义比较器类,并实现其中的compare方法。然后,在MapReduce作业的配置中设置自定义比较器类。 例如,以下是一个使用自定义比较器MapReduce程序的示例: ```java import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.Reducer; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; public class WordCount { public static class MyMapper extends Mapper<Object, Text, Text, IntWritable>{ private final static IntWritable one = new IntWritable(1); private Text word = new Text(); public void map(Object key, Text value, Context context ) throws IOException, InterruptedException { StringTokenizer itr = new StringTokenizer(value.toString()); while (itr.hasMoreTokens()) { word.set(itr.nextToken()); context.write(word, one); } } } public static class MyReducer extends Reducer<Text,IntWritable,Text,IntWritable>
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值